Applying Machine Learning Models as Clinical Decision Support (CDS) Tools to Assist Clinician’s Decision Making in Critical Care

Clinical decision-support (CDS) tools aim to enhance healthcare decision-making, with the final objective to improve the quality of care from healthcare providers. As clinical practice moves into an era of personalized therapy, the research and application of CDS tools in electronic health record systems will enhance operating efficiencies for healthcare providers in critical care and optimize treatment recommendations for subgroups and individual patients. Data from intensive care units (ICU) can be useful for learning about patients as they were collected in a data-rich environment. A large amount of data can then be fed into artificial intelligence (AI) systems (using computers to mimic human cognitive functions) and machine learning methods (using computer algorithms to perform clinical tasks without the need for explicit instructions). Given the dynamic nature of critically ill patients, one machine learning method called reinforcement learning (RL) is particularly suitable for ICU settings. With the improvement of data collection and advancement in machine learning technologies, Siqi’s research sees great potential of RL models to be served as CDS tools to optimize treatment recommendations in critical care and to impact the discovery of novel therapeutic methods in personalized healthcare.